Jongmin Lee
Jongmin Lee
Embedded Files
Hi! I am a postdoctoral researcher at the University of Pennsylvania, working with Nikolai Matni. Previously, I obtained a Ph.D. at Seoul National University under the supervision of Ernest K. Ryu.
My research focuses on the theoretical foundations of optimization algorithms. In particular, I am interested in leveraging optimization techniques to analyze and enhance the convergence of reinforcement learning and deep learning algorithms.
Contact : jongmlee@engineering.upenn.edu
Publications
Publications
(C: Conference: J: Journal, P: Preprint, *: Equal contribution)
(C: Conference: J: Journal, P: Preprint, *: Equal contribution)
[C7] Policy Gradient Algorithms in Average-Reward Multichain MDPs
Jongmin Lee, Ernest K. Ryu
[C6] Finite-Time bounds for Average-Reward Fitted Q-Iteration
Jongmin Lee, Ernest K. Ryu
[C5] Near-Optimal Sample Complexity for MDPs via Anchoring
Jongmin Lee*, Mario Bravo*, Roberto Cominetti*
[C4] Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Process
Jongmin Lee, Ernest K. Ryu
[C3] Accelerating Value Iteration with Anchoring
Jongmin Lee, Ernest K. Ryu
[C2] Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
Jongmin Lee, Joo Young Choi, Ernest K. Ryu, Albert No
[C1] A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast
Jongmin Lee, Chanwoo Park, Ernest K. Ryu
[J3] Minimax-optimal Halpern iterations for Lipschitz maps
Mario Bravo*, Roberto Cominetti*, Jongmin Lee*
Mathematical Programming, 2026
[J2] Deflated Dynamics Value Iteration
Jongmin Lee, Amin Rakhsha, Ernest K Ryu, Amir-massoud Farahmand
[J1] Convergence Analyses of Davis-Yin Splitting via Scaled Relative Graphs
Jongmin Lee*, Sohuen Yi*, Ernest K. Ryu
[P3] M-duality in fixed-point problems for general normed spaces
Jongmin Lee*, Sangyeop Woo*, Ernest K. Ryu,
arxiv, 2026
[P2] Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process
Jongmin Lee, Ernest K. Ryu, Vaneet Aggarwal
arxiv, 2026
[P1] Why Policy Gradient Algorithms Work for Undiscounted Total-Reward MDPs
Jongmin Lee, Ernest K. Ryu
arxiv, 2025
Education
Education
Seoul National University (SNU), Sep 2023 - August 2026 (advisor: Ernest K. Ryu)
Ph.D. in Mathematics
Seoul National University (SNU), Sep 2020 - August 2023 (advisor: Ernest K. Ryu)
M.S. in Mathematics
Korea Advanced Institute of Science and Technology (KAIST), Mar 2012 - Feb 2020
B.S. in Mathematics
Experiences
Experiences
Postdoctoral researcher, University of Pennsylvania, Sep 2026 - present (Nikolai Matni)
Collaboration, Purdue University, Mar 2026 - May 2026 (Vaneet Aggarwal)
Collaboration, Pontificia Universidad Católica de Chile, Dec 2024 - Feb 2025 (Roberto Cominetti and Mario Bravo)
Research Intern, Vector Institute, May 2023 - Aug 2023 (Amir-massoud Farahmand)
Military Service, Army sergeant, Sep 2015 - June 2017
Invited talks
Invited talks
Purdue Seminar, Apr 2026, "Enhancing Average-Reward Reinforcement Learning via Anchoring"
INFORMS, Oct 2025, "Enhancing Average-Reward Reinforcement Learning via Anchoring"
RL theory seminar, Feb 2025, "Accelerating Value Iteration with Anchoring"
AGCO seminar, University of Chile, Aug 2024, "Convergence Analysis of Davis-Yin Splitting via Scaled Relative Graph"
Awards
Awards
Youlchon Fellowship, SNU AI, 2022
Page updated
Report abuse